Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Speaking" followed by a person's name or title and a related speech or statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Speaking"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finder
    -0.74
     no
    -0.62
    cule
    -0.60
     determined
    -0.60
     initiation
    -0.59
     tornado
    -0.58
     seed
    -0.58
     99
    -0.57
     pim
    -0.57
     found
    -0.57
    POSITIVE LOGITS
    Speaking
    3.46
     Speaking
    2.71
    Talking
    1.98
    Writing
    1.47
    Asked
    1.37
    speaking
    1.35
    Anyway
    1.35
     speaking
    1.34
    Regarding
    1.29
    Lastly
    1.26
    Act Density 0.021%

    No Known Activations